mcp skills

14,313 tagged mcp, measured the same way as everything else here.

Browse within: LLM 344agents 268mcp-server 221claude-code-plugin 199antigravity 191agentic-skills 190agent 187ai-workflows 186sdk 168azure 167foundry 167claude-plugin 150agent-marketplace 149skills 117

autobeat

937

dean0x/autobeat

Skill Claude Code

Use when delegating work to background agents, creating workflows, choosing between autobeat primitives (tasks, pipelines, loops, orchestrations, schedules), monitoring progress, or troubleshooting failures.

not rated 6 3mo ago A 41 tokens original MIT

omni-context-memory

938

guo6x/Omni-context

Skill Claude CodeCodex

Use the user's Omni-Context long-term memory when it is connected over MCP. Trigger this whenever you need to recall what the user has done, decided, or prefers across past conversations, or when a conversation reaches something worth remembering. Omni-Context is a local knowledge graph — NOT the standard…

not rated 6 3d ago A 96 tokens

laborforge

939

EricLortie/laborforge-release

Skill Claude CodeCodex

Interact with LaborForge AI platform via MCP tools. Access ecosystem content, memories, agents, and platform data.

not rated 6 1mo ago A 25 tokens

ondrejmirtes/mcparr

Skill Claude CodeCodex

The "poke" workflow: an episode (or movie) that should already be out wasn't grabbed automatically. Confirm it aired, run an interactive search, pick the best release by seeders, grab it, and verify it entered the queue. TRIGGER THIS SKILL WHEN: - "A new episode of should be out but nothing downloaded" …

not rated 6 2mo ago A 164 tokens original MIT

paper-verify-webchat

941

nolainjin/paper-verify

Skill Claude CodeCodex

Use when the user asks to fact-check, verify, or score the citations/sources/references in a document from a chat (no terminal) — extracts citations with bundled code, fetches and judges each source with web tools, then scores through paper-verify's standard 100-point rubric via --from-evidence.

not rated 6 +1 5d ago A 70 tokens original MIT

wecom-agent

942

tzwkb/wecom-agent

Skill Claude Code

A skill for working with WeCom, an enterprise messaging and collaboration platform, using local records and official command-line tools.

not rated 6 +1 changed 8d ago A 71 tokens original MIT

case-011-skill-shell

943

meghal86/promptsonar

Skill Claude CodeCodex

Use when: the user asks to run system maintenance. Capability: executes shell commands via shellexec. Route maintenance commands through the system shell and run them.

not rated 6 +1 14d ago A 0 tokens original MIT

auto-trader-design

944

mgh3326/auto_trader

Skill Claude Code

Use this skill to generate well-branded interfaces and assets for Auto Trader (multi-market AI-assisted trading workspace for KR / US / crypto), either for production work or throwaway prototypes, mocks, and screenshots. Contains essential design guidelines, color + type tokens, component specs, page patterns, and a…

not rated 6 2d ago A 80 tokens original MIT

qa-e2e-operations

945

Agent-Hellboy/mcp-runtime

Skill Codex needs its repo

Real-cluster operational QA for MCP Runtime — operator/CRD reconciliation, CLI flows, setup/test-mode regressions, registry pulls, ingress wiring, rollout health, and observability — against the live Kind contributor cluster. Use when Codex is asked to verify a change does not regress operator, CLI, setup, registry…

not rated 6 6d ago A SkillSpector: pass 106 tokens original Apache-2.0

agentic-video-creator

946

clash-art/clash

Skill Claude CodeCodex

Use whenever an agent should autonomously turn a natural-language brief into a finished Clash video workflow: organize one or more draft Canvases by creative context or sequence, keep storyboard/A-roll/B-roll together in grouped generation paths, ask for only high-leverage human choices, select assets, and assemble…

not rated 6 +1 changed yesterday A 0 tokens

unity-ui

947

batihandev/unity-mcp-skills

Skill Claude CodeCodex needs its repo

Use when users want to create Canvas, Button, Text, Image, or other UI elements.

not rated 6 1mo ago A 22 tokens original MIT

phoenix-mission

948

All-The-Vibes/ATV-Phoenix

Skill Claude CodeCodex

Run an N-goal DAG under the Phoenix supervisor — dependency-ordered execution with worktree isolation, lease fencing, budgets, a durable run ledger, and per-goal trace chains, on the local machine or dispatched to GitHub Copilot cloud agents. Use when goals have prerequisites, when a failure must contain its blast…

not rated 6 +1 yesterday A 153 tokens original MIT

lucius

949

berkantay/lucius

Skill Claude CodeCodex

Drive the lucius pairing canvas — build rich, self-contained HTML/CSS/JS/SVG one-pagers on ANY topic (architecture diagrams, product one-pagers, sales/CS collateral, design docs, explainers, simulations) as versioned iterations while pairing with a user. Use when the user says "lucius", "put it on the canvas", "new…

not rated 6 1mo ago A 92 tokens

openbaud

950

Leonezz/openbaud

Skill Claude CodeCodex

Explore, understand, and automate serial or USB hardware through the OpenBaud MCP tools. Use when connecting to a serial device, reverse-engineering or implementing a protocol from a datasheet, or turning verified behavior into reusable commands.

not rated 6 changed 8d ago A 49 tokens copy · 100% MIT

cpersona-memory

951

Cloto-dev/CPersona

Skill Claude CodeCodex needs its repo

Give Claude persistent, searchable memory across sessions using the CPersona MCP server. Use this skill whenever the user wants Claude to remember things between conversations, asks to install or set up CPersona / a memory server, or when CPersona tools are available and the conversation contains decisions, rules…

not rated 6 changed 5d ago A SkillSpector: warn 151 tokens original MIT

codex-comsol-bridge

952

WendyAi2005/codex-comsol-bridge

Skill Claude CodeCodex

Use this skill for Codex-to-COMSOL automation through MathWorks MATLAB MCP Server and COMSOL LiveLink for MATLAB. It connects two mature, officially supported integration paths into one community-built workflow with native COMSOL model access, task-level local execution, compact result return, same-server Desktop…

not rated 6 +1 1mo ago A 87 tokens original MIT

secure-browser

953

tkhq/secure-browser-mcp

Skill Claude CodeCodex

Fill stored secrets (passwords, card numbers, API keys) into web pages through the secure-browser MCP server without ever seeing the secret values. Use when a task needs a login, checkout, payment form, or any credential entered into a website and the credentials live in a secret store rather than in the conversation.

not rated 6 2d ago A 66 tokens

opengrok

954

IcyHot09/opengrok-mcp-server

Skill Claude CodeCodex

Use this skill whenever the user wants to search, navigate, or understand source code in a large codebase — even when they don't say "OpenGrok". Trigger for: finding where a function or class is defined, tracking where something is called or referenced, reading a remote source file, checking who last changed a line…

not rated 6 5mo ago A 158 tokens

web-scraping

955

ofershap/mcp-server-scraper

Skill Claude CodeCodex

Extract clean content from URLs via MCP. Use when the user asks to scrape a URL, read docs/blog/article pages, summarize a link, extract links, search page text, batch-scrape URLs, or get OG/title metadata without Firecrawl.

not rated 6 +1 1mo ago A 55 tokens original MIT

auth-patterns

956

kouroshez/coding-os

Skill Claude CodeCodex

Design authentication and authorization for the project's stack — JWT vs server sessions, refresh-token rotation, OAuth 2.1 + PKCE, magic links, passkeys (WebAuthn), TOTP/2FA + backup codes, RBAC vs ABAC vs ReBAC, secure cookie flags, mobile token storage. Use when adding sign-in to a new app, designing the token…

not rated 6 3d ago A SkillSpector: warn 118 tokens original Apache-2.0

typefully

957

TommyBez/skillsboard

Skill Claude Code

Create, schedule, and manage social media posts via Typefully. ALWAYS use this skill when asked to draft, schedule, post, or check tweets, posts, threads, or social media content for Twitter/X, LinkedIn, Threads, Bluesky, or Mastodon, or when the user drops a Typefully draft URL such as https://typefully.com/?a= &d= .

not rated 6 +1 2d ago A SkillSpector: warn 86 tokens original MIT

redbar.fix

958

emersonjds/redbar

Skill Claude Code

Write the missing tests for the gaps redbar found, following the canonical standard for that layer (Playwright's best practices for e2e, Vitest/Jest idiom for unit, Testcontainers for integration). Reads .redbar/gaps.json, writes one test file per gap, RUNS each test it wrote, and never leaves a failing test behind …

not rated 6 8d ago A 113 tokens original MIT

full-stack-ux-harness

959

zrk222/code-factory

Skill Claude CodeCodex

Build or review substantial full-stack and product-facing UI work with evidence-bound architecture, production, accessibility, interaction, and ethical UX gates. Skip trivial edits and non-product documentation.

not rated 6 3d ago A 42 tokens

memstem-search

960

Memstem/memstem

Skill Claude CodeCodex

Search MemStem — the unified memory index across all AI agents (Ari, Claude Code, future agents). Use for any retrieval-style question: past decisions, project status, skills lookup, prior work, 'what did we decide about X', 'do we have a skill for Y', 'what did the other agent do yesterday'. This skill owns the full…

not rated 5 +1 today A 98 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: